McGill University research into how we digest poetry could wind up helping computer programs boost computer speech
A McGill University researcher Michael Wagner says his research into how we read and hear poetry could provide insights useful to programmers seeking to improve how computers speak.
“Voice synthesis has become quite impressive in terms of the pronunciation of individual words,” Wagner says. “But when a computer ‘speaks,’ whole sentences still sound artificial because of the complicated way we put emphasis on parts of them, depending on context and what we want to get across.”
In particular, Wagner and fellow researcher Katherine McCurdy of Harvard University, have explored differences in how English and French speakers evaluate poetry. One difference is in the French acceptance of rhymes like “right” and “write,” whereas this is frowned upon in English poetry. Their focus is on something called “prosody,” which refers to the rhythm, emphasis and flow of speech (Their findings have been published in the journal Cognition).
Follow AlphaDoggs on Facebook
Follow Bob on Twitter at www.twitter.com/alphadoggs
